INDEX

Explanations

terms and names related to scientific and medical research

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 deportivos

-0.41

iri

-0.40

engesch

-0.38

 podido

-0.37

 pohled

-0.36

 civiles

-0.36

cham

-0.36

 podjet

-0.36

 frequência

-0.35

 izdel

-0.35

POSITIVE LOGITS

 nahilalakip

0.98

Vidite

0.97

PreferredItem

0.85

 AssemblyCulture

0.82

 "..\..\

0.80

 BrowserModule

0.79

httphttps

0.77

UrlResolution

0.76

 AssemblyTitle

0.76

 мәкал

0.76

Activations Density 3.728%

terms and names related to scientific and medical research

No Comments

No Known Activations